Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     немного
    -0.07
    .nr
    -0.06
     panties
    -0.06
     Vladim
    -0.06
     stickers
    -0.06
    Pix
    -0.06
     obr
    -0.06
     Holiday
    -0.06
     opciones
    -0.06
     údaj
    -0.06
    POSITIVE LOGITS
    axis
    0.07
    utta
    0.07
    typeorm
    0.07
     '(
    0.06
     lake
    0.06
    hf
    0.06
     classes
    0.06
    ToOne
    0.06
     advantageous
    0.06
    eor
    0.06
    Act Density 0.113%

    No Known Activations